Overview

Online news services such as Microsoft News have gained huge popularity for online news reading. However, since massive news articles are published everyday, users of online news services are facing heavy information overload. Therefore, news recommendation is an important technique for personalized news services to improve the reading experience of users and alleviate information overload.

However, news recommendation is a challenging task. First, news articles on news websites emerge and update very quickly. Many new articles are posted continuously, and existing news articles will disappear after a short period of time. Thus, there is a severe cold-start problem in news recommendation. Second, news articles usually contain rich textual information such as title and body. It is very important to understand news content from their texts using NLP techniques. Third, there is no explicit rating of news articles posted by users in news platforms. Thus, in news recommendation we need to model users’ interests from their browsing and click behaviors. However, user interests are usually diverse and dynamic, which poses significant challenges to user modeling algorithms. Thus, further researches are highly needed to tackle the various challenges in news recommendation.

To promote the research and practice on news recommendation, we hold a MIND News Recommendation Competition based on the MIND dataset, which is a large-scale English dataset for news recommendation. This challenge will provide a good testbed for participants to develop better news recommender systems to improve the future reading experience of millions of users.


Following is a step-by-step tutorial for this competition:


Winners

Grand Prize

  • Huige Cheng, Sogou, China (chenghuige)

    • Second Place Prizes

  • U Kang, Seoul National University and DeepTrade Inc., South Korea (dtsnu)
  • Yichao Lu, Layer 6 AI, Canada (oahciy)

    • Third Place Prizes

  • Mathieu Ravaut, Independent, France (Ravox)
  • Qin Ruan, University College Dublin, Ireland (Qinne)
  • Congcong Gu, PingAn, China (gcc_microsoft)
  • Zhenghong Yang, Hangzhou Dianzi University, China (YangZhenghong)

    • Leaderboard

    Rank Team AUC MRR nDCG@5 nDCG@10

    1

    Sept. 11, 2020     		chenghuige 0.7131 0.3608 0.3960 0.4521

    2

    Sept. 11, 2020     		dtsnu 0.7114 0.3568 0.3916 0.4485

    3

    Sept. 11, 2020     		oahciy 0.7096 0.3540 0.3883 0.4454

    4

    Sept. 11, 2020     		Ravox 0.7048 0.3505 0.3845 0.4416

    5

    Sept. 11, 2020     		Qinne 0.7032 0.3496 0.3830 0.4397

    6

    Sept. 11, 2020     		gcc_microsoft 0.6979 0.3479 0.3806 0.4373

    7

    Sept. 11, 2020     		YangZhenghong 0.6975 0.3474 0.3803 0.4373

    8

    Sept. 11, 2020     		xyzhang 0.6970 0.3471 0.3809 0.4379

    9

    Sept. 11, 2020     		huailei 0.6968 0.3492 0.3812 0.4386

    10

    Sept. 11, 2020     		hanyan 0.6964 0.3441 0.3764 0.4336

    11

    Sept. 11, 2020     		lixmcm 0.6952 0.3438 0.3765 0.4335

    12

    Sept. 11, 2020     		Tmail 0.6952 0.3433 0.3755 0.4327

    13

    Sept. 11, 2020     		duchunning 0.6951 0.3430 0.3755 0.4326

    14

    Sept. 11, 2020     		fanxiaoxing 0.6946 0.3448 0.3771 0.4335

    15

    Sept. 11, 2020     		overlord 0.6942 0.3445 0.3767 0.4332

    16

    Sept. 11, 2020     		veason 0.6941 0.3433 0.3749 0.4319

    17

    Sept. 11, 2020     		WONNIU 0.6929 0.3423 0.3730 0.4301

    18

    Sept. 11, 2020     		Ironball 0.6923 0.3440 0.3778 0.4351

    19

    Sept. 11, 2020     		wcy419hh 0.6915 0.3410 0.3711 0.4282

    20

    Sept. 11, 2020     		AndreaChao 0.6903 0.3413 0.3727 0.4299

    21

    Sept. 11, 2020     		Ivy 0.6901 0.3414 0.3726 0.4299

    22

    Sept. 11, 2020     		changebin 0.6888 0.3396 0.3706 0.4273

    23

    Sept. 11, 2020     		Tsar 0.6862 0.3374 0.3676 0.4253

    24

    Sept. 11, 2020     		heroddaji 0.6845 0.3376 0.3677 0.4244

    25

    Sept. 11, 2020     		amgis3 0.6836 0.3318 0.3615 0.4193

    26

    Sept. 11, 2020     		fit4you 0.6835 0.3325 0.3628 0.4210

    27

    Sept. 11, 2020     		again_and_again 0.6828 0.3365 0.3665 0.4240

    28

    Sept. 11, 2020     		xinghuaz 0.6816 0.3357 0.3666 0.4239

    29

    Sept. 11, 2020     		dengjia284 0.6814 0.3325 0.3614 0.4192

    30

    Sept. 11, 2020     		ustc_jingang 0.6809 0.3337 0.3633 0.4208

    31

    Sept. 11, 2020     		qqyysg 0.6799 0.3336 0.3644 0.4213

    32

    Sept. 11, 2020     		majinc 0.6798 0.3322 0.3624 0.4196

    33

    Sept. 11, 2020     		Reto-hitsz 0.6786 0.3283 0.3572 0.4151

    34

    Sept. 11, 2020     		shahnawaz 0.6766 0.3282 0.3576 0.4149

    35

    Sept. 11, 2020     		yupei 0.6765 0.3321 0.3619 0.4193

    36

    Sept. 11, 2020     		CyberFish 0.6730 0.3343 0.3647 0.4219

    37

    Sept. 11, 2020     		zidane4ever21 0.6710 0.3236 0.3523 0.4093

    38

    Sept. 11, 2020     		dust 0.6691 0.3267 0.3539 0.4109

    39

    Sept. 11, 2020     		xcw 0.6554 0.3172 0.3434 0.4000

    40

    Sept. 11, 2020     		HJS_TJU 0.6512 0.3122 0.3357 0.3934

    41

    Sept. 11, 2020     		AND-OR 0.6506 0.3079 0.3320 0.3898

    42

    Sept. 11, 2020     		simple2better 0.6490 0.3088 0.3341 0.3918

    43

    Sept. 11, 2020     		gaojx 0.6346 0.3105 0.3350 0.3909

    44

    Sept. 11, 2020     		TJ_Arthur 0.6282 0.2945 0.3162 0.3738

    45

    Sept. 11, 2020     		tcchiang 0.5950 0.2794 0.2974 0.3551

    46

    Sept. 11, 2020     		learner 0.5845 0.2639 0.2775 0.3349

    47

    Sept. 11, 2020     		only2233 0.5352 0.2408 0.2507 0.3075

    48

    Sept. 11, 2020     		cs880141 0.5182 0.2316 0.2384 0.2941

    49

    Sept. 11, 2020     		Jenny 0.5157 0.2336 0.2411 0.2966

    50

    Sept. 11, 2020     		cdj0311 0.5062 0.2279 0.2338 0.2887

    51

    Sept. 11, 2020     		zhoubang1 0.5010 0.2248 0.2306 0.2860

    52

    Sept. 11, 2020     		q710245300 0.5006 0.2242 0.2297 0.2858

    53

    Sept. 11, 2020     		SatyadevNtv 0.5002 0.2241 0.2298 0.2851

    54

    Sept. 11, 2020     		bird 0.4367 0.1957 0.1954 0.2489